PublicVision: A Secure Smart Surveillance System for Crowd Behavior Recognition

PublicVision: защищённая интеллектуальная система видеонаблюдения для распознавания поведения толпы
Yin Yang, Marwa Qaraqe, Emrah Başaran, Almiqdad Elzein, Elizabeth B. Varghese, Wisam Costandi, Jack Rizk, Nasim Alam
2024-01-01

Dynamic Multipoint VPNIPSecSwin Transformercrowd behavior recognitionsecure video surveillance
Crowd behavior recognition plays a critical role in various domains, including public safety, event management, and urban planning. Understanding crowd dynamics and detecting behaviors based on violence levels are crucial for preventing incidents and maintaining order in crowded environments. However, traditional surveillance methods fall short of providing comprehensive and real-time insights into complex crowd behavior patterns and fail to distinguish different violence levels within crowds that affect proactive decision-making. Moreover, most of the current systems do not provide reliable secure data transmission and are not viable in protecting the privacy of individuals. This paper designs an end-to-end secure and smart surveillance system, namely PublicVision, that transmits CCTV data securely to a remote central hub where a deep learning (DL) model based on Swin Transformer is utilized to identify and analyze crowd behaviors. A novel video dataset was created to train the DL model that identifies crowds based on size and violence level. The proposed system incorporates end-to-end security by creating a Dynamic Multipoint Virtual Private Network (DMVPN) and leverages the property of IP Security (IPSec) and Firewall for confidentiality and integrity during transmission and storage. Experiment analysis and real-time inference using DeepStream Software Development Kit (SDK) proved that the proposed system has significant implications for public safety, security, and crowd management in various contexts, including public spaces, transportation hubs, and large-scale events.
1
A Swin Transformer-based deep learning model identifies crowds according to crowd size and violence level, addressing limitations of conventional surveillance systems.
2
Experiments and real-time DeepStream SDK inference demonstrated the system’s applicability to public safety, transportation hubs, public spaces, and large-scale events.
3
PublicVision provides an end-to-end smart surveillance architecture that securely transmits CCTV data to a remote central hub for automated crowd analysis.
4
The authors created a novel video dataset for training the crowd behavior recognition model.
5
The system integrates DMVPN, IPSec, and firewalls to protect transmitted and stored surveillance data through confidentiality and integrity mechanisms.

Crowds in CCTV-monitored public environments

Crowd behavior recognition and analysis by crowd size and violence level, with secure and privacy-preserving surveillance data transmission

Publication Details
Publication Date
2024-01-01
Journal
Publisher
ISSN
Cited by
112
Access Type
Author Information
Authors
Yin Yang
Marwa Qaraqe
Emrah Başaran
Almiqdad Elzein
Elizabeth B. Varghese
Wisam Costandi
Jack Rizk
Nasim Alam
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%